-
### Description
**What problem are you trying to solve?**
We are running custom Karpenter implementation with k3s
We would like to extend to have one Karpenter handling multi region support i…
-
### Description
This spike aims to draft the initial architecture of Kyma Companion agents, focusing on high-priority capabilities, their communication, interaction with external systems, and ensurin…
-
A much lighter alternative to/subset of #14798.
Following services need to be configured:
1. A few Mina nodes to be used for experiment setup
- 1 seed, 3 bps, 5 regular nodes, 1 snark coord…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Description
Hi
I'm working with your code in the current days and I guess it will be used for our productio…
-
### 🚀 The feature
**TL;DR \-** We want to lean into **modular Multi-Threading/Multi-Processing** instead of the current monolithic Multi-Processing, and steer users away from the monolithic Datase…
-
It's helpfull to simplify designing middleware/app which take care paired nodes, in other words request/response communication, such as in ISO-14229 UDS(Unified Diagnostic Services).
In a diagnosti…
-
Has anyone considered adapting `llama_multiprocess` to run on multiple machines instead of multiple processes? I've started by using the `SystemCommunicator` from `rsmpi` library to replace `nccl::Com…
-
### Current Behavior
Currently, in th e run overview, we can get an idea of the system hardware, specifically GPU count and CPU count. However, as far as I can tell this does not account for multi-no…
-
- [x] I have marked all applicable categories:
+ [ ] exception-raising bug
+ [ ] RL algorithm bug
+ [ ] documentation request (i.e. "X is missing from the documentation.")
+ [x] ne…
-
### 🚀 The feature, motivation and pitch
As we can see, Google Gemini can support up to million tokens and to serve longer context length, we have to do context parallelism, which means, split the i…